Batch Remove Image Backgrounds with Python and PaddlePaddle

Preparation

We first install the PaddlePaddle deep‑learning framework (CPU version) via pip and verify the installation, then install PaddleHub.

python -m pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple

import paddle.fluid
paddle.fluid.install_check.run_check()

pip install -i https://mirror.baidu.com/pypi/simple paddlehub

Code Implementation

The workflow consists of importing the module, loading the model, collecting image files, and calling the segmentation API.

import os, paddlehub as hub
huseg = hub.Module(name='deeplabv3p_xception65_humanseg')  # load model
path = './imgs/'                                          # image folder
files = [path + i for i in os.listdir(path)]              # file list
results = huseg.segmentation(data={'image': files})       # perform cutout

Place the source pictures in the imgs directory; after running the script the cut‑out images are saved in humanseg_output with the same filenames but PNG format.

Example original images:

Resulting cut‑out images:

Conclusion

This short script demonstrates how PaddlePaddle and PaddleHub can batch‑process image background removal with only a few lines of Python code, saving time for developers who need quick visual editing.